Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6375 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1081. Min Range: -7.1081
Max Act: 7.1081. Min Act: -0.1700
Data Index: 7466929 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1081. Min Range: -7.1081
Max Act: 7.0768. Min Act: -0.1700
Data Index: 8818 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1081. Min Range: -7.1081
Max Act: 7.0768. Min Act: -0.1700
Data Index: 2993315 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 6531057 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 6037844 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 2111888 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9518. Min Act: -0.1700
Data Index: 4597723 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9518. Min Act: -0.1700
Data Index: 4011661 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9518. Min Act: -0.1700
Data Index: 542294 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9206. Min Act: -0.1700
Data Index: 8772714 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9206. Min Act: -0.1700
Data Index: 5396244 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9518. Min Act: -0.1700
Data Index: 1090088 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.9206. Min Act: -0.1700
Data Index: 973789 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8893. Min Act: -0.1700
Data Index: 7852370 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8893. Min Act: -0.1700
Data Index: 1101840 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8893. Min Act: -0.1700
Data Index: 5480413 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8893. Min Act: -0.1700
Data Index: 7039140 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8893. Min Act: -0.1700
Data Index: 6241237 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8268. Min Act: -0.1700
Data Index: 7655963 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1081. Min Range: -7.1081
Max Act: 6.8268. Min Act: -0.1700
Data Index: 2805191 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19